Claude Haiku 5.5 Benchmarks, Pricing & Rankings
Anthropic · 2026-10-07 · Closed · Current
Snapshot 2026-10-14 · updated weekly
Claude Haiku 5.5 ranks #16 of 42 on the AMR leaderboard.
Claude Haiku 5.5 benchmark scores
| GPQA Diamond | 83.2% | |
| MMLU-Pro | 81.5% | |
| SWE-Bench Verified | 64.7% | |
| AIME 2025 | 82.8% | |
| LiveCodeBench v6 | 73.4% | |
| Arena Elo | 1402 |
Claude Haiku 5.5 price, speed & context
Input price
$0.80
per 1M tokens
Output price
$4
per 1M tokens
Speed
232
tok/s
Context
500K
tokens
About Claude Haiku 5.5
Claude Haiku 5.5 is the newest small Anthropic model: its benchmark jump over Haiku 5 is the largest generation-over-generation gain in the small-model class, at $0.80/$4 per million tokens.
Models around Claude Haiku 5.5 in the rankings
More Anthropic models
Claude Haiku 5.5 FAQ
Where does Claude Haiku 5.5 rank?
Claude Haiku 5.5 ranks #16 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 87.9. Its strongest dimension is GPQA Diamond at 83.2%.
How much does Claude Haiku 5.5 cost?
Claude Haiku 5.5 costs $0.80 per million input tokens and $4 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $3.20 per million tokens.
What is the Claude Haiku 5.5 context window?
Claude Haiku 5.5 supports a 500K token context window and generates at a median 232 output tokens per second. That context fits roughly 333 standard documents in a single prompt.
Is Claude Haiku 5.5 open source?
No — Claude Haiku 5.5 is a closed model available only through Anthropic’s official API and authorized cloud partners.
What is better than Claude Haiku 5.5?
MiniMax H3 ranks one place higher at #15 with an AMR score of 88.2. Claude Haiku 5.5 still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.